Deploying and managing models

Use Watson Machine Learning to deploy models and solutions so that you can put them into productive use, then monitor the deployed assets for fairness and explainability. You can also automate the AI lifecycle to keep your machine learning assets current.

Completing the AI lifecycle

After you prepare your data and build then train models or solutions, you complete the AI lifecycle by deploying and monitoring your assets.

Deployment is the final stage of the lifecycle of a model or script, where you run your models and code. Watson Machine Learning provides the tools that you need to deploy an asset, such as a machine learning model or function, or a Decision Optimization solution.

Following deployment, you can use model management tools to evaluate your models. IBM Watson OpenScale tracks and measures outcomes from your AI models, and helps ensure they remain fair, explainable, and compliant. Watson OpenScale also detects and helps correct the drift in accuracy when an AI model is in production.

Finally, you can use Watson Studio Pipelines to manage your ModelOps processes. Create a pipeline that automates parts of the AI lifecycle, such as training and deploying a machine learning model.

Next steps

• Find out how to manage assets in a deployment space
• Find out how to deploy assets from a deployment space
• View sample notebooks that demonstrate deploying that uses the Python client or REST API

• Evaluate your deployed models for bias by using Watson OpenScale

• Learn how to deploy Decision Optimization solutions

Parent topic: Watson Machine Learning